Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Reached 150k population for the first time on Cities Skylines 2. The game starts to get really choppy after ~120k though. It was interesting to see, how initially GPU was at 100% utilisation but CPU at 10% and by the time you reach 100k population, even CPU cranks up... show more

Arnav Gupta

74,573 subscribers

13,027 views • 1 year ago •via X (Twitter)

Gaming Science & Technology Education

Anya Rossi• Live Now

Private livecam show

10 Comments

Arnav Gupta1 year ago

Each human walking there, each car, each signal, each flight path - all of that is deterministic logic - of a complexity of multiple orders more than what I can ever imagine to wrangle in my head. City simulation games humble me like nothing else. 🥹

Arnav Gupta1 year ago

I don't think I can ever even have the slightest of feeling that I am a good software engineer who can deal with a lot of complexity, as long as I keep playing these games. It reminds me right back - just how much more complex games are than your typical consumer internet app.

Arnav Gupta1 year ago

Ugh sorry for the colors, I had HDR on when playing, which made the recording an HDR recording - which plays back fine on my PC but uploading to Twitter made this all washed out because Twitter doesn’t convert it back to SDR with a high contrast color grade I guess.

NetMind.AI2 years ago

Get access to a wide range of GPUs like H100, A100, 4090, 3090 and save over 90% at NetMind Power. Rent Now!

Saksham1 year ago

Min requirements at which you are running this? I bought this game but haven’t played it yet due to limitations on my laptop.

Mohamed Siddique1 year ago

I love this game but this is one reason why I don’t play much 🥲

Ved Antani1 year ago

This is awesome - you got 3070 ?

Arnav Gupta1 year ago

No this is on a laptop-grade 4090, which I think is slightly worse than a desktop grade 4080. (Didn't build a PC here, just bought the top end Razer Blade)

paneeerkapakoda1 year ago

How do you manage to keep the money in +

Anil1 year ago

not your PC's fault. game is poorly optimized

Related Videos

Stress testing Metropolis 1998! - Population: 53,500 - CPU FPS: 80 - GPU FPS: 10-80 - RAM: 3,100 MB So: At the moment, the game is GPU bound. I know why and there's a lot of room for improvement. It will involve developing or customizing an existing GPU framework. There's also a lot of room to improve CPU/RAM, but right now it's in an okay place. #gamedev

Stress testing Metropolis 1998! - Population: 53,500 - CPU FPS: 80 - GPU FPS: 10-80 - RAM: 3,100 MB So: At the moment, the game is GPU bound. I know why and there's a lot of room for improvement. It will involve developing or customizing an existing GPU framework. There's also a lot of room to improve CPU/RAM, but right now it's in an okay place. #gamedev

Yesbox - Metropolis 1998

84,873 views • 1 year ago

HOW TO ATTACK AFTER FIRST-TIME INCISIVE NERF ✏️🚨 ✅ Pinged Pass+ has become a MUST ✅ Lengthy is really important ✅ Bugs every defender ✅ Breaks CPU rats I thought it was impossible to make the game worse, but they did it 😂

HOW TO ATTACK AFTER FIRST-TIME INCISIVE NERF ✏️🚨 ✅ Pinged Pass+ has become a MUST ✅ Lengthy is really important ✅ Bugs every defender ✅ Breaks CPU rats I thought it was impossible to make the game worse, but they did it 😂

Rysu

190,786 views • 4 months ago

Current 2x RTX 6000 build during an extended bench test. CPU at 100% and both GPUs at 100%. Recorded for noise and thermals documentation. This is as loaded as I can get it on the 1600w titanium PSU. Pulling ~1650w at the wall. People were interested in how the air cooled HX on the CPU would hold up so wanted to document. Cruises at about 95c even with the GPUs going nuts. Had to cap GPUs around 535w for the test, that was just being safe with the PSU ceiling (got within 50w of the PSU hard cap) and I wanted to put maximum emphasis for this test on the CPU cooler under full load at the full 350w draw with GPU exhaust hitting it. It genuinely holds up like a champ. It feels like my limits with this build at this point are power not thermals.

Current 2x RTX 6000 build during an extended bench test. CPU at 100% and both GPUs at 100%. Recorded for noise and thermals documentation. This is as loaded as I can get it on the 1600w titanium PSU. Pulling ~1650w at the wall. People were interested in how the air cooled HX on the CPU would hold up so wanted to document. Cruises at about 95c even with the GPUs going nuts. Had to cap GPUs around 535w for the test, that was just being safe with the PSU ceiling (got within 50w of the PSU hard cap) and I wanted to put maximum emphasis for this test on the CPU cooler under full load at the full 350w draw with GPU exhaust hitting it. It genuinely holds up like a champ. It feels like my limits with this build at this point are power not thermals.

Mike Bradley

29,134 views • 2 months ago

the new --cpu-prof flag is a really nice way to see how much of your time Bun is spending on the CPU ⚡ you can open the profile directly in VSCode/Cursor/Chrome DevTools. also makes it easier to compare how your script performs in Bun vs Node!

Lydia Hallie ✨

70,061 views • 8 months ago

I learned how to use the GPU Profiler, and I was able to optimize the game enough that even I can play it at 100% resolution and around 60fps now! And that's with the screen recorder going too. Turns out there was a render target eating up about 20fps this whole time!

I learned how to use the GPU Profiler, and I was able to optimize the game enough that even I can play it at 100% resolution and around 60fps now! And that's with the screen recorder going too. Turns out there was a render target eating up about 20fps this whole time!

DRIG

15,283 views • 9 months ago

How To Beat The CPU Every Time This Sunday we’re getting a Gauntlet-style CPU event where you have to go 10–0 to earn a 95 OVR BND Super Bowl player. You can beat the CPU consistently by calling this play. Formation: Nickel 3-3 Dbl Mug Play: Mid Blitz Setup 1.Pull The Safety Manned Up To The HB Over The Center 2.Tap UP on the D-Pad to open the Substitution Menu (this player-locks you). 3.Hold DOWN on the left stick. 4.Engage the center as the ball is snapped. Hopefully this was helpful! Feel free to Bookmark this for later, and Follow Me, Hexied, for more Madden content like this!

How To Beat The CPU Every Time This Sunday we’re getting a Gauntlet-style CPU event where you have to go 10–0 to earn a 95 OVR BND Super Bowl player. You can beat the CPU consistently by calling this play. Formation: Nickel 3-3 Dbl Mug Play: Mid Blitz Setup 1.Pull The Safety Manned Up To The HB Over The Center 2.Tap UP on the D-Pad to open the Substitution Menu (this player-locks you). 3.Hold DOWN on the left stick. 4.Engage the center as the ball is snapped. Hopefully this was helpful! Feel free to Bookmark this for later, and Follow Me, Hexied, for more Madden content like this!

Hexied

89,118 views • 5 months ago

the person anxin wanted to get close with at the first meeting was xinlong "if you see xinlong for the first time, he looks old. like... he was born in 1998" im crying 😭 "but xinlong is really nice"

the person anxin wanted to get close with at the first meeting was xinlong "if you see xinlong for the first time, he looks old. like... he was born in 1998" im crying 😭 "but xinlong is really nice"

۠

105,765 views • 9 months ago

I'm very happy, even though it's just a bronze medal.This match was like a roller coaster for me.After the first game,I was a little confused and didn't even know how to play.Also in the first half of the second game.I told myself at that time,think about it again.Try other ways.

I'm very happy, even though it's just a bronze medal.This match was like a roller coaster for me.After the first game,I was a little confused and didn't even know how to play.Also in the first half of the second game.I told myself at that time,think about it again.Try other ways.

Twee Twee

87,754 views • 1 year ago

ImDontai reacts to PlaqueBoyMax's "Thong Song" for the first time, instantly starts vibing, and even had to replay it because of how catchy it was 😭🔥

ImDontai reacts to PlaqueBoyMax's "Thong Song" for the first time, instantly starts vibing, and even had to replay it because of how catchy it was 😭🔥

PlaqueBoyMaxUpdates

125,806 views • 1 month ago

This gentleman was using the restroom at the rest area and came out to find out his semi was struck by another truck driver. The other driver starts yelling at him about how he was parked despite being the one who hit the other semi truck. The gentleman wanted to call the police and the other truck driver refused, claiming that it was a waste of time. I’m not even sure if the truck driver understands what he even did, but to avoid further escalation, would you just call the cops at this point even though you may have no damages?

This gentleman was using the restroom at the rest area and came out to find out his semi was struck by another truck driver. The other driver starts yelling at him about how he was parked despite being the one who hit the other semi truck. The gentleman wanted to call the police and the other truck driver refused, claiming that it was a waste of time. I’m not even sure if the truck driver understands what he even did, but to avoid further escalation, would you just call the cops at this point even though you may have no damages?

SonnyBoy🇺🇸

156,346 views • 4 months ago

Brock Purdy on his favorite play in his career: “It was the game before the NFCCG against the Packers. We didn’t play the best on offense, but we needed this drive at the end of the game to go up. It was a 3rd down play and it was Brandon Aiyuk over the middle. We call it Gucci. It was a 6 step slant, cross the nickel’s face. It was man to man coverage, and it was on time. I threw it on plant, BA turned at the right time. It was tight coverage. DB reached across. We got the ball there and it was a diving catch. I was like 'Bro', boom we get the first down. We’re staying on the field. From there we won the game. We won the NFC Championship game after that. We got to the Super Bowl, but it was that play. If that play didn’t happen, getting to the NFCCG and the Super Bowl wouldn’t have happened… Those are the things I remember. I love that stuff. I live for it.” 🎥: Richard Sherman

Brock Purdy on his favorite play in his career: “It was the game before the NFCCG against the Packers. We didn’t play the best on offense, but we needed this drive at the end of the game to go up. It was a 3rd down play and it was Brandon Aiyuk over the middle. We call it Gucci. It was a 6 step slant, cross the nickel’s face. It was man to man coverage, and it was on time. I threw it on plant, BA turned at the right time. It was tight coverage. DB reached across. We got the ball there and it was a diving catch. I was like 'Bro', boom we get the first down. We’re staying on the field. From there we won the game. We won the NFC Championship game after that. We got to the Super Bowl, but it was that play. If that play didn’t happen, getting to the NFCCG and the Super Bowl wouldn’t have happened… Those are the things I remember. I love that stuff. I live for it.” 🎥: Richard Sherman

Coach Yac 🗣

86,444 views • 11 months ago

That legendary moment when the boss himself arrived at court for the battle for humanity The scammers knew their time was up, and it was finally time to pack up and get out

That legendary moment when the boss himself arrived at court for the battle for humanity The scammers knew their time was up, and it was finally time to pack up and get out

SMX 🇺🇸

402,039 views • 2 months ago

It was interesting to see what the Nets did with Egor Dëmin at the end of the game last night. The ball really flowed through Nolan Traore, and Dëmin was expected to spot up. He made a three, but I wonder how this hierarchy of sorts will pan out.

It was interesting to see what the Nets did with Egor Dëmin at the end of the game last night. The ball really flowed through Nolan Traore, and Dëmin was expected to spot up. He made a three, but I wonder how this hierarchy of sorts will pan out.

FLOOR and CEILING (Wilko)

23,520 views • 1 year ago

we work get new macbook air m4 16/256 Apple M4 chip, featuring a 10-core CPU and up to a 10-core GPU, delivers cutting-edge performance and efficiency to the MacBook Air M4, positioning you at the forefront of technology. kes 123,000 call 0707311340 or visit

we work get new macbook air m4 16/256 Apple M4 chip, featuring a 10-core CPU and up to a 10-core GPU, delivers cutting-edge performance and efficiency to the MacBook Air M4, positioning you at the forefront of technology. kes 123,000 call 0707311340 or visit

🇰🇪Kype Computers 🇹🇿🇺🇬

16,021 views • 7 months ago

At #TheFantasticFour premiere, Ralph Ineson describes what it was to see Galactus for the first time

At #TheFantasticFour premiere, Ralph Ineson describes what it was to see Galactus for the first time

The Hollywood Reporter

25,766 views • 11 months ago

And then again in 2007! They really were trying to get Beyoncé (& other celebrities) to shade Britney Spears at the time just because it was “cool” to hate on her at the time.

And then again in 2007! They really were trying to get Beyoncé (& other celebrities) to shade Britney Spears at the time just because it was “cool” to hate on her at the time.

(Fan) Britney Crave

13,638 views • 3 months ago

"It was brilliant to get a win. It was a great feeling to go down the tunnel 3-0 up at half-time and for the supporters to feel that they had witnessed a really good first-half performance." David Moyes' #EVETOT verdict:

"It was brilliant to get a win. It was a great feeling to go down the tunnel 3-0 up at half-time and for the supporters to feel that they had witnessed a really good first-half performance." David Moyes' #EVETOT verdict:

Everton

189,833 views • 1 year ago

Oh, that one time Alex Rodriguez came back to Seattle for the first time after leaving for the Rangers. It was such a big deal ESPN's Baseball Tonight was at the Mariners game capturing all the hate A-Rod got. Alex Rodriguez left for a landmark 10-year, $252 million deal which was the largest in sports history at the time 💰

Oh, that one time Alex Rodriguez came back to Seattle for the first time after leaving for the Rangers. It was such a big deal ESPN's Baseball Tonight was at the Mariners game capturing all the hate A-Rod got. Alex Rodriguez left for a landmark 10-year, $252 million deal which was the largest in sports history at the time 💰

ON Tap Sports Trivia

169,990 views • 2 months ago

PowerInfer - a high-speed inference engine for deploying LLMs locally. Just came across this super interesting project on speeding up inference. It's not MoE but it's a simple approach that exploits the high locality in LLM inference to design a GPU-CPU hybrid inference engine. Hot-activated neurons are preloaded onto the GPU for fast access, while cold-activated neurons (the majority) are computed on the CPU. This approach significantly reduces GPU memory demands and CPU-GPU data transfer. It achieves an average token generation rate of 13.20 tokens/s, with a peak of 29.08 tokens/s, across various LLMs on a single NVIDIA RTX 4090 GPU. It's on only 18% lower than that achieved by a top-tier server-grade A100 GPU. It also significantly outperforms llama.cpp by up to 11.69x while retaining model accuracy. There is a lot more innovation around inference that's coming fast. Really encouraged by the study on sparse computation to enhance the computational efficiency of LLMs. It's now possible to use PowerInfer with Llama 2 and Faclon 40B. Mistral-7B support is coming soon!

PowerInfer - a high-speed inference engine for deploying LLMs locally. Just came across this super interesting project on speeding up inference. It's not MoE but it's a simple approach that exploits the high locality in LLM inference to design a GPU-CPU hybrid inference engine. Hot-activated neurons are preloaded onto the GPU for fast access, while cold-activated neurons (the majority) are computed on the CPU. This approach significantly reduces GPU memory demands and CPU-GPU data transfer. It achieves an average token generation rate of 13.20 tokens/s, with a peak of 29.08 tokens/s, across various LLMs on a single NVIDIA RTX 4090 GPU. It's on only 18% lower than that achieved by a top-tier server-grade A100 GPU. It also significantly outperforms llama.cpp by up to 11.69x while retaining model accuracy. There is a lot more innovation around inference that's coming fast. Really encouraged by the study on sparse computation to enhance the computational efficiency of LLMs. It's now possible to use PowerInfer with Llama 2 and Faclon 40B. Mistral-7B support is coming soon!

elvis

261,622 views • 2 years ago